cw-dogfood

cw-dogfood is a skill for Claude Code, Codex from Hmbown/Codewhale. It costs 52 tokens per session (1,390 once invoked), scanned A, original, MIT.

A workflow for testing a code change in the real product after automated checks pass. It builds a stamped release binary, installs it, verifies the fresh shell, and performs manual checks that tests may miss.

In plain words
What is it for?
Use it for user-visible changes, release candidates, runtime bug fixes, or requests to build, install, or try the local binary.
Why use it?
Automated tests can pass while the installed application still has runtime, display, input, or approval-flow problems. This process checks the software as a user would run it.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for codewhale. Also seen: mentions AGENTS.md; built for codewhale.

Good fit Use it for user-visible changes, release candidates, runtime bug fixes, or requests to build, install, or try the local binary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/codewhale/cw-dogfood
About the project

Codewhale is an open-source coding agent that runs in the terminal and can read repositories, edit files, execute commands, and inspect results while pursuing a task. Developers use it with hosted providers or local models, with controls for how much access it receives.

Hmbown/Codewhale · 40,935 stars · on GitHub · codewhale.net

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Hmbown/Codewhale --skill cw-dogfood
Clone the repo
git clone --depth 1 https://github.com/Hmbown/Codewhale

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cw-dogfood

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmbown/codewhale/cw-dogfood/github.svg)](https://agentmods.dev/skills/hmbown/codewhale/cw-dogfood)
Your own site
<a href="https://agentmods.dev/skills/hmbown/codewhale/cw-dogfood"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/cw-dogfood/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cw-dogfood

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/codewhale/cw-dogfood"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/cw-dogfood.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 6 Sept 2026 📄 Read the review Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 106
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01390
Opus 5 $0.00026 $0.00695
Sonnet 5 $0.00010 $0.00278
Haiku 4.5 $0.00005 $0.00139

Measured 4d ago against content hash 43d7c8f8d288, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cw-dogfood scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/skills/cw-dogfood/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cw-dogfood

Green gates prove the code compiles and asserts. They do not prove the product works. Freezes, route contamination, focus theft, streaming cadence, and approval-flow regressions all live in the runtime, where no unit test looks. This stage puts the actual binary on your PATH and makes you use it.

Stage 4 of the loop: cw-orientcw-slicecw-gatesdogfoodcw-landcw-handoff.

When to use

  • The change is user-visible: TUI layout, motion, streaming, model or Fleet selection, approvals, commands, install paths.
  • Before landing a release candidate, or before claiming a runtime behavior is fixed.
  • Hunter asks to "install the build", "dogfood this", or "get this on my machine".

Workflow

  1. Gate first. Run cw-gates to the rung the change deserves. Never install an ungated build.

  2. Build stamped. Local builds are unstamped ((dev)) since #5245, and the installer refuses an unstamped binary on purpose — the stamp is what proves the thing on your PATH is the thing you just built:

    CODEWHALE_BUILD_SHA=$(git rev-parse HEAD) \
      cargo build --release --locked -p codewhale-cli -p codewhale-tui
    
  3. Install atomically. Use the script; do not hand-copy:

    scripts/release/install-dogfood.sh          # defaults to target/release
    

    It refuses a dirty source tree (override deliberately with CODEWHALE_ALLOW_DIRTY_DOGFOOD=1, and then say so wherever you report the install), verifies the binary embeds current HEAD, installs codewhale and codew into ~/.cargo/bin and ~/.local/bin (override with CODEWHALE_INSTALL_DIRS), re-signs ad-hoc on macOS, and verifies resolution from a fresh login shell.

    Never cp over a running binary. On Apple Silicon that poisons the kernel's code-signature cache for the inode, and later execs hang until reboot. The installer does tmp-copy plus atomic mv for exactly this reason.

Read the full file on GitHub · 115 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 115 lines · 52 tokens per session scan A 43d7c8f8d288

Subscribe to this mod's changes

cw-dogfood is a skill published in the GitHub repository Hmbown/Codewhale (40,935 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,390 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.